Related papers: Scalable Synthesis of Verified Controllers in Deep…
Safe exploration is a common problem in reinforcement learning (RL) that aims to prevent agents from making disastrous decisions while exploring their environment. A family of approaches to this problem assume domain knowledge in the form…
We introduce a hybrid (discrete--continuous) safety controller which enforces strict state and input constraints on a system---but only acts when necessary, preserving transparent operation of the original system within some safe region of…
While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints. A growing line of work addresses this problem by modifying the model's sampling policy at decoding time using…
Erroneous behaviour in safety critical real-time systems may inflict serious consequences. In this paper, we show how to synthesize timed shields from timed safety properties given as timed automata. A timed shield enforces the safety of a…
Deep learning operators are fundamental components of modern deep learning frameworks. With the growing demand for customized operators, it has become increasingly common for developers to create their own. However, designing and…
The advent of Text-to-Image generative models poses significant risks of copyright violation and deepfake generation. Since the rapid proliferation of new copyrighted works and private individuals constantly emerges, reference-based…
This paper tackles the problem of generating safe exit controllers for continuous-time systems described by stochastic differential equations (SDEs). The primary aim is to develop controllers that maximize the lower bounds of the exit…
Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising approach for training reasoning language models (RLMs) by leveraging supervision from verifiers. Although verifier implementation is easier than solution…
The objective of this research is to enable safety-critical systems to simultaneously learn and execute optimal control policies in a safe manner to achieve complex autonomy. Learning optimal policies via trial and error, i.e., traditional…
Safe Reinforcement Learning focuses on developing optimal policies while ensuring safety. A popular method to address such task is shielding, in which a correct-by-construction safety component is synthesized from logical specifications.…
Learning-based approaches for controlling safety-critical systems are rapidly growing in popularity; thus, it is important to assure their performance and safety. Hamilton-Jacobi (HJ) reachability analysis is a popular formal verification…
Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, existing scaling methods have key limitations: parallel…
Synthetic verification techniques such as generating test cases and reward modelling are common ways to enhance the coding capabilities of large language models (LLM) beyond predefined tests. Additionally, code verification has recently…
Deep reinforcement learning (RL) is an optimization-driven framework for producing control strategies for general dynamical systems without explicit reliance on process models. Good results have been reported in simulation. Here we…
Implicit models such as Deep Equilibrium Models (DEQs) have emerged as promising alternative approaches for building deep neural networks. Their certified robustness has gained increasing research attention due to security concerns.…
This paper develops a data-driven safe control framework for nonlinear discrete-time systems with parametric uncertainty and additive disturbances. The proposed approach constructs a data-consistent closed-loop representation that enables…
This paper introduces several techniques that improve the scalability of the deductive verification of data-level programs working on arrays and matrices. First of all, we introduce a technique to rewrite expressions with (nested)…
The verification and validation of cyber-physical systems is known to be a difficult problem due to the different modeling abstractions used for control components and for software components. A recent trend to address this difficulty is to…
Deep Active Learning (DAL) aims to reduce labeling costs in neural-network training by prioritizing the most informative unlabeled samples for annotation. Beyond selecting which samples to label, several DAL approaches further enhance data…
Controller synthesis for hybrid systems that satisfy temporal specifications expressing various system properties is a challenging problem that has drawn the attention of many researchers. However, making the assumption that such temporal…